© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 163399
    Prev
    Next
    INDEX
    Explanations

    Code/formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ec
    -0.30
     calle
    -0.27
    羣æŃ£
    -0.27
    (Locale
    -0.27
    æľ¬å¸Ĥ
    -0.27
    Matt
    -0.26
    Rua
    -0.26
    ÐĻ
    -0.25
    tru
    -0.25
     tep
    -0.24
    POSITIVE LOGITS
    rzy
    0.26
    иÑĩно
    0.26
    ndon
    0.25
    pite
    0.25
    ITED
    0.24
    posables
    0.24
    icare
    0.24
    lasses
    0.24
    lectic
    0.24
    regor
    0.24
    Activations Density 0.007%

    No Known Activations