© 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. 162609
    Prev
    Next
    INDEX
    Explanations

    hunger and appetite

    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
    otch
    -0.32
    jal
    -0.31
    iales
    -0.30
    idential
    -0.26
    èĢIJå¿ĥ
    -0.25
    人æĢ§
    -0.24
    uber
    -0.24
    渺
    -0.24
    гÑĢан
    -0.24
    çĸ¯
    -0.23
    POSITIVE LOGITS
    .BL
    0.30
    è´Ł
    0.26
    sÅĤ
    0.26
     amore
    0.25
     sensations
    0.24
    amen
    0.24
    éĵĥ
    0.24
     Already
    0.24
    éļ¾åº¦
    0.24
    Already
    0.24
    Activations Density 0.002%

    No Known Activations