© 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. 27-TRANSCODER-HP
    7. 58020
    Prev
    Next
    INDEX
    Explanations

    names and locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĺ¯ä¸Ģ家
    -0.26
    åı¯ä»¥è¯´æĺ¯
    -0.26
    anged
    -0.26
    rous
    -0.26
     omission
    -0.25
    sheets
    -0.25
    scp
    -0.25
    oton
    -0.25
    ä¸įæŃ¢
    -0.24
    sip
    -0.24
    POSITIVE LOGITS
     overhead
    0.27
    åŃ£åº¦
    0.27
     annual
    0.26
    adier
    0.26
    bullet
    0.26
    éģ
    0.25
     dresser
    0.25
    avigator
    0.24
    è¦ĭç©į
    0.24
    mdat
    0.24
    Activations Density 0.785%

    No Known Activations