© 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. 23-TRANSCODER-HP
    7. 24391
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     guarantee
    -0.28
     guarantees
    -0.25
    éĶ¡
    -0.25
    Plans
    -0.25
    ="+
    -0.24
     Provid
    -0.24
    coat
    -0.24
    kü
    -0.24
    elters
    -0.24
    å§Ĵ
    -0.24
    POSITIVE LOGITS
    -alpha
    0.25
    quan
    0.24
    ensive
    0.24
    Domin
    0.24
    ->{$
    0.24
    å®ļå¾ĭ
    0.24
    inations
    0.23
    ç¹ģ
    0.23
    符åı·
    0.23
    è¯ķè¡Į
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.