© 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. 54159
    Prev
    Next
    INDEX
    Explanations

    medical/scientific texts

    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
    éro
    -0.34
    æ²ī积
    -0.29
    å¹²
    -0.29
    yan
    -0.28
    å¸ĥæĭī
    -0.28
    ozo
    -0.28
    gid
    -0.28
    å¢ŀ强
    -0.28
    imm
    -0.27
    acro
    -0.27
    POSITIVE LOGITS
    tesy
    0.28
     Ksi
    0.28
    èĭŀ
    0.28
     Buster
    0.26
     bans
    0.26
    åĽĽæĺ¯
    0.25
    esy
    0.24
    dsp
    0.24
     lesbi
    0.24
    æħ·
    0.24
    Activations Density 0.044%

    No Known Activations