© 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. 12-TRANSCODER-HP
    7. 23236
    Prev
    Next
    INDEX
    Explanations

    heat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĨĬ
    -0.28
     good
    -0.27
    //}}
    -0.27
     separating
    -0.26
     separates
    -0.25
    -inc
    -0.25
    oland
    -0.24
    æĥ¯ä¾ĭ
    -0.24
     separated
    -0.24
    好
    -0.24
    POSITIVE LOGITS
    çŃĶ
    0.28
    âľª
    0.27
    天æ°Ķ
    0.26
    ijkl
    0.25
     ride
    0.25
    å¾Ĺèµ·
    0.25
    主管éĥ¨éŨ
    0.25
     reprint
    0.25
     markup
    0.24
    ivitÃł
    0.24
    Activations Density 0.000%

    No Known Activations