© 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. 33-TRANSCODER-HP
    7. 53281
    Prev
    Next
    INDEX
    Explanations

    Computer technology

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å·´æĭī
    -0.29
     Tear
    -0.27
    rina
    -0.26
    çªĿ
    -0.25
    è®®
    -0.25
    :view
    -0.25
    SYM
    -0.24
     Benton
    -0.24
    ä½łè¯´
    -0.24
    åŁİå¸Ĥåıijå±ķ
    -0.24
    POSITIVE LOGITS
    <|endoftext|>
    0.35
     alerts
    0.34
     defenses
    0.33
     lesions
    0.33
     equations
    0.33
     controls
    0.32
     locks
    0.32
     programs
    0.32
    ’s
    0.31
     shocks
    0.31
    Activations Density 0.095%

    No Known Activations