© 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. 32-TRANSCODER-HP
    7. 43515
    Prev
    Next
    INDEX
    Explanations

    agg

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    neas
    -0.28
    etration
    -0.27
    zte
    -0.26
     mounts
    -0.26
    Urls
    -0.26
    liner
    -0.25
    avis
    -0.25
    tas
    -0.25
    <quote
    -0.25
    åıijå±ķ
    -0.24
    POSITIVE LOGITS
    ubern
    0.26
    isper
    0.25
    ur
    0.25
    èī¯
    0.25
    asonry
    0.24
     Mafia
    0.24
    Prosec
    0.24
    æ¾Ħæ¸ħ
    0.24
    omencl
    0.24
    æŁ¥å¤Ħ
    0.24
    Activations Density 0.000%

    No Known Activations