© 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. 25-TRANSCODER-HP
    7. 107775
    Prev
    Next
    INDEX
    Explanations

    technical lists/documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    |;↵
    -0.28
    ãĢij,ãĢIJ
    -0.26
    );}↵↵
    -0.26
     "-";↵
    -0.26
     */;↵
    -0.26
    abileceÄŁi
    -0.26
     ðŁĺī↵↵
    -0.26
    imeo
    -0.25
    scription
    -0.24
    );?>↵
    -0.24
    POSITIVE LOGITS
    :
    0.46
    ï¼ļ
    0.39
     :
    0.37
    :**
    0.32
    .
    0.31
    :this
    0.31
    .:
    0.30
    ":
    0.30
     Re
    0.28
    :\
    0.28
    Activations Density 1.023%

    No Known Activations