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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 19-TRANSCODER-HP
    4. 5661
    Prev
    Next
    INDEX
    Explanations

    hyphens

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ients
    -0.26
    ICODE
    -0.25
    举
    -0.25
     candidates
    -0.25
     candidacy
    -0.25
     unsuccessfully
    -0.25
     patched
    -0.24
    åĢĻéĢī
    -0.24
    èĪī
    -0.24
     fishes
    -0.24
    POSITIVE LOGITS
    ieber
    0.30
    emet
    0.30
    immutable
    0.27
    Fu
    0.26
    ç°¿
    0.25
    ç¨İ
    0.25
    emachine
    0.25
    åıijå±ķè¶ĭåĬ¿
    0.25
    .middleware
    0.25
    毫
    0.25
    Activations Density 0.056%

    No Known Activations