© 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. 19-TRANSCODER-HP
    7. 5804
    Prev
    Next
    INDEX
    Explanations

    Social media posts

    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
    haft
    -0.26
    å¾Ĥ
    -0.26
    ($)
    -0.25
    arResult
    -0.25
    emails
    -0.25
    æ©Ľ
    -0.24
    èĢĮåıĪ
    -0.24
    ilan
    -0.24
    ABILITY
    -0.24
    æı©
    -0.23
    POSITIVE LOGITS
    unting
    0.26
    ÑĭваÑĤÑĮ
    0.25
    rame
    0.25
    æİĴè¡Į
    0.24
     Doming
    0.23
    iece
    0.23
    缴æĴŃ
    0.23
    注æĺİåĩºå¤Ħ
    0.23
    å§ĵåIJį
    0.23
    æ°´æĻ¶
    0.23
    Activations Density 0.009%

    No Known Activations