© 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. 53989
    Prev
    Next
    INDEX
    Explanations

    on

    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
    å°¾
    -0.32
    Tail
    -0.31
     Tail
    -0.31
     power
    -0.30
     Power
    -0.30
     tail
    -0.30
    è®®
    -0.28
    oard
    -0.28
     on
    -0.28
    Power
    -0.27
    POSITIVE LOGITS
    getti
    0.28
    åŁºéĩij管çIJĨ
    0.27
    liness
    0.26
    etten
    0.26
    ENTIC
    0.26
    ellas
    0.26
    tees
    0.26
    elters
    0.26
    SenderId
    0.25
    gee
    0.25
    Activations Density 0.019%

    No Known Activations