© 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. 163488
    Prev
    Next
    INDEX
    Explanations

    direct

    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
    ,[],
    -0.30
    orer
    -0.29
    è´¨éĩıåĴĮ
    -0.29
    itage
    -0.27
    irth
    -0.26
    ,"%
    -0.25
    çŃī级
    -0.24
    isoft
    -0.24
    loat
    -0.24
     Announcement
    -0.24
    POSITIVE LOGITS
    ly
    0.38
    离å¼ĢäºĨ
    0.28
    à¹Ĩ
    0.27
    nya
    0.27
     fac
    0.26
    aly
    0.26
    ivities
    0.26
    ives
    0.25
    line
    0.25
    /em
    0.24
    Activations Density 0.061%

    No Known Activations