© 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. 9-TRANSCODER-HP
    7. 29877
    Prev
    Next
    INDEX
    Explanations

    Mixed snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Brun
    -0.29
    åıijæĮ¥äºĨ
    -0.26
    nameof
    -0.25
    powers
    -0.25
    åºķéĥ¨
    -0.25
    ****/↵
    -0.25
    ***/↵↵
    -0.25
    åIJİåı°
    -0.25
    ’an
    -0.24
     Queens
    -0.24
    POSITIVE LOGITS
    .Double
    0.29
    ofil
    0.26
    ouch
    0.25
     reap
    0.25
    ç»ķ
    0.24
     pork
    0.24
     travel
    0.24
    ì§ģ
    0.24
    unde
    0.24
    omy
    0.24
    Activations Density 0.244%

    No Known Activations