© 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. 53317
    Prev
    Next
    INDEX
    Explanations

    orthodontic and medical treatments

    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
    pire
    -0.31
    åĪ©
    -0.29
    ç©¿è¶Ĭ
    -0.26
    çĭ¬
    -0.26
    icity
    -0.25
    esen
    -0.25
    æİ¥ä¸ĭæĿ¥
    -0.25
    oner
    -0.25
    lic
    -0.24
    adies
    -0.24
    POSITIVE LOGITS
    /problem
    0.26
     Cah
    0.25
    ekte
    0.25
    opa
    0.25
    ilogy
    0.25
    strand
    0.24
    constraints
    0.24
    éĤ¶
    0.24
     ceilings
    0.24
    .AF
    0.24
    Activations Density 0.018%

    No Known Activations