© 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. 20-TRANSCODER-HP
    7. 63334
    Prev
    Next
    INDEX
    Explanations

    English language text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĬ©
    -0.30
    åIJįå½ķ
    -0.29
    onas
    -0.28
    第ä¸ĢæĿ¡
    -0.28
    çī©
    -0.28
    anches
    -0.26
    ç»İ
    -0.26
    enko
    -0.26
    [::-
    -0.26
    .mvp
    -0.25
    POSITIVE LOGITS
    çĩĶ
    0.29
    im
    0.27
     STATES
    0.26
    éĤ¦
    0.25
     connection
    0.25
    åıijè¨Ģ
    0.24
    ç§
    0.24
    å±IJ
    0.24
     States
    0.24
    殡
    0.23
    Activations Density 25.569%

    No Known Activations