© 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. 24133
    Prev
    Next
    INDEX
    Explanations

    component

    np_max-act · gemini-2.0-flash
    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
     Keystone
    -0.25
    thesis
    -0.25
    anna
    -0.25
    诣
    -0.24
    ovation
    -0.23
    举åįĹ
    -0.23
    lik
    -0.23
    cope
    -0.22
    peak
    -0.22
    Peak
    -0.22
    POSITIVE LOGITS
    InChildren
    0.28
    наÑĤ
    0.27
    ocab
    0.26
    ä¸ĢèĤ¡
    0.26
    lap
    0.25
     lap
    0.24
    èĤ¡
    0.24
    ä¸Ģåı£
    0.24
    æŁľ
    0.24
    ailable
    0.23
    Activations Density 0.334%

    No Known Activations