© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 162507
    Prev
    Next
    INDEX
    Explanations

    negative experiences

    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
    -Russian
    -0.27
    alore
    -0.26
    -urlencoded
    -0.25
     Clar
    -0.25
    INCT
    -0.25
    ymous
    -0.25
    encil
    -0.24
    æ´»æĢ§çĤŃ
    -0.24
    egis
    -0.24
    ä½Ĩ她
    -0.24
    POSITIVE LOGITS
    社ä¼ļ
    0.35
    ç»ıæµİæįŁå¤±
    0.32
    èĩ´
    0.32
     societal
    0.31
    å¾Ī
    0.31
    athe
    0.31
     risks
    0.30
     impact
    0.30
     stress
    0.29
    æįŁå¤±
    0.29
    Activations Density 0.021%

    No Known Activations