© 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. 53992
    Prev
    Next
    INDEX
    Explanations

    B

    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
    楽
    -0.27
    ç§ij
    -0.26
    缺
    -0.26
    íĿ¥
    -0.26
    Score
    -0.26
    ró
    -0.25
    ед
    -0.25
     ver
    -0.25
    ixer
    -0.24
    edic
    -0.24
    POSITIVE LOGITS
    aten
    0.28
    bane
    0.27
    initely
    0.26
    ä½ĵåĨħ
    0.25
     Doyle
    0.25
    atum
    0.25
    .fm
    0.25
    arma
    0.25
    ä¿Ŀç½Ĺ
    0.25
    иÑĤа
    0.25
    Activations Density 0.029%

    No Known Activations