© 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. 53225
    Prev
    Next
    INDEX
    Explanations

    in

    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
    ver
    -0.30
    chied
    -0.30
     van
    -0.29
     Burlington
    -0.29
     im
    -0.29
     ir
    -0.27
    åĬ©çIJĨ
    -0.27
     ind
    -0.27
    _ptr
    -0.27
    INGTON
    -0.26
    POSITIVE LOGITS
    ate
    0.41
    é£Ł
    0.28
    stime
    0.27
    se
    0.27
    å¯Įè´µ
    0.27
    mirror
    0.26
    ès
    0.25
     ÐļÑĥ
    0.25
    iss
    0.25
    sex
    0.25
    Activations Density 0.012%

    No Known Activations