© 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. 24-TRANSCODER-HP
    7. 150966
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arry
    -0.30
    éĹ¾
    -0.28
    aper
    -0.28
    ordo
    -0.28
    inct
    -0.26
    ,...↵↵
    -0.26
    roi
    -0.25
    aturing
    -0.25
    insi
    -0.24
    alone
    -0.24
    POSITIVE LOGITS
    红线
    0.30
     Mind
    0.30
    illis
    0.28
    köp
    0.27
    éĺŁåijĺ们
    0.27
    è¿Ļ款
    0.27
    è¿ĻéĩĮæĺ¯
    0.26
    è¿ĻéĩĮ
    0.26
    é¾Ļæ³ī
    0.26
     here
    0.26
    Activations Density 1.021%

    No Known Activations