Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 23-TRANSCODER-HP
    4. 8192
    Prev
    Next
    INDEX
    Explanations

    I

    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
    pez
    -0.28
    _NAV
    -0.26
     SID
    -0.25
    SID
    -0.25
    mania
    -0.25
    份
    -0.24
    _SID
    -0.24
    avy
    -0.24
     floated
    -0.24
    é¡¶
    -0.23
    POSITIVE LOGITS
    antium
    0.27
    æľ¬ç½ij
    0.26
    ÑİÑīим
    0.26
     deciding
    0.26
     offend
    0.25
     lurking
    0.25
     incest
    0.25
    führer
    0.24
    asting
    0.24
     Obtain
    0.24
    Activations Density 0.036%

    No Known Activations