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. 14882
    Prev
    Next
    INDEX
    Explanations

    between

    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
    _HOR
    -0.28
     differ
    -0.27
    çͷ女
    -0.27
    _hor
    -0.27
     prevention
    -0.26
     Hamm
    -0.26
    åĽłæŀľ
    -0.26
     layer
    -0.26
    hor
    -0.26
    Hor
    -0.26
    POSITIVE LOGITS
    åłĩ
    0.29
    _PROD
    0.27
    {}]
    0.27
    >".
    0.26
     failing
    0.26
     Koch
    0.25
     Banks
    0.25
    exas
    0.25
    >'.
    0.24
    those
    0.23
    Activations Density 0.017%

    No Known Activations