© 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. 30-TRANSCODER-HP
    7. 96321
    Prev
    Next
    INDEX
    Explanations

    (

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sl
    -0.31
    -mon
    -0.28
    OLF
    -0.27
     passive
    -0.26
    avar
    -0.25
    olf
    -0.25
    å°ģéĹŃ
    -0.25
    pp
    -0.25
    Off
    -0.25
     Tues
    -0.25
    POSITIVE LOGITS
    (os
    0.33
     os
    0.32
    ç½Ĺæĸ¯
    0.32
     Gros
    0.32
    os
    0.31
    ros
    0.30
    -os
    0.29
    rosse
    0.29
    ots
    0.29
    .os
    0.29
    Activations Density 0.937%

    No Known Activations