© 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. 11-RESID-POST-AA
    11. 1395
    Prev
    Next
    INDEX
    Explanations

    Code and Russian text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    澳大
    -0.07
     financ
    -0.07
    陕西省
    -0.07
    	Collection
    -0.07
     Imag
    -0.07
     restarted
    -0.07
     embarked
    -0.07
    Elim
    -0.06
     analytical
    -0.06
    yer
    -0.06
    POSITIVE LOGITS
    _('
    0.07
     ưu
    0.07
     وه
    0.07
     паци
    0.07
     sb
    0.07
    .cm
    0.07
    几种
    0.06
    ьев
    0.06
    quiet
    0.06
    />↵
    0.06
    Activations Density 0.224%

    No Known Activations