© 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. 5766
    Prev
    Next
    INDEX
    Explanations

    URLs and code fragments

    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
    Nr
    -0.08
    〈
    -0.07
    kJ
    -0.07
    <num
    -0.07
    esthesia
    -0.07
    出现问题
    -0.07
    	UFUNCTION
    -0.07
     Sud
    -0.07
    芡
    -0.07
     fungal
    -0.07
    POSITIVE LOGITS
     facil
    0.08
    	ast
    0.07
    .W
    0.07
     terminate
    0.07
    container
    0.06
    UNDLE
    0.06
    .Log
    0.06
     rais
    0.06
    isé
    0.06
    嘻
    0.06
    Activations Density 0.007%

    No Known Activations