© 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. 162471
    Prev
    Next
    INDEX
    Explanations

    earth metals

    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
    MARY
    -0.27
    èĩ¾
    -0.27
    SPELL
    -0.25
    ç¼®
    -0.25
     defensively
    -0.25
    férence
    -0.24
    nard
    -0.24
    ously
    -0.23
    (spell
    -0.23
    imately
    -0.23
    POSITIVE LOGITS
    æ²Ļ
    0.29
    ä¼½
    0.28
     minerals
    0.27
     nuclei
    0.27
    çłĤ
    0.26
    çħ¤
    0.26
    çŁ¿å±±
    0.26
    è§Ĥ
    0.26
    -earth
    0.25
    noxious
    0.25
    Activations Density 0.018%

    No Known Activations