© 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. 30-TRANSCODER-HP
    7. 95640
    Prev
    Next
    INDEX
    Explanations

    factor

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bite
    -0.25
     Turnbull
    -0.25
    -scalable
    -0.25
    æĭĩ
    -0.25
    CallCheck
    -0.24
    å¤ĸæı´
    -0.23
    lish
    -0.23
     Explosion
    -0.23
     identities
    -0.23
    èħ¾
    -0.23
    POSITIVE LOGITS
     factor
    1.59
     Factor
    1.40
    factor
    1.37
    Factor
    1.33
    -factor
    1.27
    åĽłåŃIJ
    1.27
    åĽłç´ł
    1.27
     factors
    1.24
    _factor
    1.20
    (factor
    1.16
    Activations Density 0.883%

    No Known Activations