© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 30-TRANSCODER-HP
    7. 95505
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    distance
    -0.31
    (distance
    -0.27
     distance
    -0.27
    atif
    -0.26
    åŁĭ
    -0.25
    Distance
    -0.25
     Distance
    -0.25
    TERN
    -0.25
    	distance
    -0.25
    ismatic
    -0.25
    POSITIVE LOGITS
    群
    0.31
    è§ĴèIJ½
    0.30
     overcrow
    0.29
    åĽļ
    0.28
     cells
    0.28
    æ§Ľ
    0.28
    çī¢
    0.28
     cages
    0.28
    -cell
    0.27
    ignant
    0.27
    Activations Density 0.102%

    No Known Activations