© 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. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 69312
    Prev
    Next
    INDEX
    Explanations

    Non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    דיון
    -0.07
    	NULL
    -0.07
    -turned
    -0.07
    )."
    -0.07
     ，
    -0.07
    亮相
    -0.07
    之处
    -0.07
     finalized
    -0.07
     blends
    -0.07
     ”
    -0.07
    POSITIVE LOGITS
     étaient
    0.07
    Inverse
    0.07
    言行
    0.07
    县政府
    0.07
    มง
    0.07
    quivo
    0.07
    𝗧
    0.07
    	Element
    0.07
    丫头
    0.07
     horizon
    0.06
    Activations Density 0.037%

    No Known Activations