© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 109270
    Prev
    Next
    INDEX
    Explanations

    please

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è®°å¾Ĺ
    -0.60
    å¿ĺäºĨ
    -0.56
    å¿ĺè®°
    -0.52
     forgot
    -0.52
    å¿ĺãĤĮ
    -0.51
    è¨ĺå¾Ĺ
    -0.49
     forgetting
    -0.48
     forget
    -0.48
     remember
    -0.46
    å¿ĺ
    -0.46
    POSITIVE LOGITS
     Mansion
    0.27
    ocol
    0.25
    ines
    0.25
     ters
    0.25
    .ct
    0.24
    imeters
    0.24
     saliva
    0.24
    atives
    0.24
    wright
    0.24
    onna
    0.24
    Activations Density 0.921%

    No Known Activations