© 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. 33-TRANSCODER-HP
    7. 54078
    Prev
    Next
    INDEX
    Explanations

    back

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     yet
    -0.31
    yet
    -0.28
    .offer
    -0.28
    åį³åı¯
    -0.28
     Invent
    -0.28
    runtime
    -0.26
     vert
    -0.25
    In
    -0.25
    ä¸Ģç³»åĪĹ
    -0.25
    带
    -0.24
    POSITIVE LOGITS
    reau
    0.30
    laÅŁma
    0.27
    æĺ¶
    0.27
    å¼¹
    0.26
    ene
    0.26
    ENE
    0.25
    .he
    0.25
    /č↵
    0.24
    iele
    0.24
    imu
    0.24
    Activations Density 0.015%

    No Known Activations