© 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. 52962
    Prev
    Next
    INDEX
    Explanations

    time periods (early, mid, late)

    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
    纳
    -0.28
    代价
    -0.28
    ioned
    -0.27
    usty
    -0.26
    íķĻêµIJ
    -0.26
    bay
    -0.26
    ion
    -0.25
    conc
    -0.24
    æĻļå¹´
    -0.24
    tera
    -0.24
    POSITIVE LOGITS
    ç¢İ
    0.28
     [+
    0.28
    elas
    0.28
    åĪĨå±Ģ
    0.26
     Six
    0.26
    six
    0.25
    ahr
    0.24
     spot
    0.24
    fec
    0.24
    åħŃ
    0.24
    Activations Density 0.026%

    No Known Activations