© 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. 32-TRANSCODER-HP
    7. 41318
    Prev
    Next
    INDEX
    Explanations

    snow

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _ring
    -0.33
    çľģæķĻèĤ²åİħ
    -0.30
    ำ
    -0.30
    ãĥľãĥ¼
    -0.29
    çīĩ
    -0.29
     ring
    -0.27
    åī¥ç¦»
    -0.26
    çݯ
    -0.26
    per
    -0.26
    in
    -0.26
    POSITIVE LOGITS
     VOL
    0.27
    обÑĭÑĤи
    0.27
    æĸŃ
    0.26
    itters
    0.25
    èĢĨ
    0.25
    OUCH
    0.25
    opa
    0.24
    ÑĤелÑĮнÑĭй
    0.24
    æ²ĥå°Ķ
    0.24
    :index
    0.24
    Activations Density 0.001%

    No Known Activations