© 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. 53116
    Prev
    Next
    INDEX
    Explanations

    code/non-English language

    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
    çĶ¨æ°´
    -0.26
    getParameter
    -0.26
    å«£
    -0.25
     yeti
    -0.25
    icum
    -0.25
    義
    -0.25
    缺
    -0.25
     masses
    -0.25
     Remain
    -0.24
     tuned
    -0.24
    POSITIVE LOGITS
    .ins
    0.28
    cle
    0.27
    idd
    0.27
    èĥģ
    0.26
    yw
    0.26
    knife
    0.25
     sap
    0.25
    lo
    0.25
    kip
    0.25
    axe
    0.25
    Activations Density 0.030%

    No Known Activations