© 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. 22-TRANSCODER-HP
    7. 98245
    Prev
    Next
    INDEX
    Explanations

    soy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esub
    -0.25
     ears
    -0.25
     eve
    -0.24
     Politico
    -0.24
    äºĨåįĬ天
    -0.24
    anian
    -0.24
    call
    -0.23
     Netanyahu
    -0.23
     buc
    -0.23
     booth
    -0.22
    POSITIVE LOGITS
    vara
    0.26
    å°¤åħ¶æĺ¯åľ¨
    0.25
    %i
    0.25
     Leave
    0.24
     Importance
    0.23
    çŁ¥èŃĺ
    0.23
    çī¹åĪ«æĺ¯åľ¨
    0.22
    以åıĬ
    0.22
    *i
    0.22
    âĢĸ
    0.22
    Activations Density 0.099%

    No Known Activations