© 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. 149778
    Prev
    Next
    INDEX
    Explanations

    residency

    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
     Serious
    -0.26
     Madness
    -0.25
     serious
    -0.25
    æįĭ
    -0.24
     fals
    -0.24
    éĹ¾
    -0.24
    ç¾Ĭ
    -0.24
    ä¸īå±Ĥ
    -0.24
     mature
    -0.23
    Customers
    -0.23
    POSITIVE LOGITS
    assa
    0.29
    us
    0.29
    ass
    0.28
    rement
    0.28
    -ass
    0.28
     qualifying
    0.28
    çĹĺ
    0.27
    ao
    0.26
    zzo
    0.26
    avern
    0.25
    Activations Density 0.158%

    No Known Activations