© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 39823
    Prev
    Next
    INDEX
    Explanations

    legal historical documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Outputs
    -0.26
     ActionTypes
    -0.26
    å±ĤéĿ¢
    -0.26
    åıijåŀĭ
    -0.26
    etcode
    -0.25
    æ°´åĪĨ
    -0.25
    _handlers
    -0.25
    æī¾åĪ°
    -0.24
    å¼ĢåıijåĮº
    -0.24
    åĤ¬åĮĸåīĤ
    -0.24
    POSITIVE LOGITS
     reckon
    0.27
     plag
    0.27
     incompet
    0.27
     confession
    0.26
     adjoining
    0.26
     hath
    0.25
     gladly
    0.25
     unlaw
    0.25
     christ
    0.25
     offending
    0.25
    Activations Density 18.238%

    No Known Activations