© 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. 89446
    Prev
    Next
    INDEX
    Explanations

    G

    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
     quarters
    -0.07
    春
    -0.07
    Add
    -0.07
     blew
    -0.07
     Memphis
    -0.07
    ='
    -0.07
    头
    -0.07
     ra
    -0.06
    ⽰
    -0.06
     floated
    -0.06
    POSITIVE LOGITS
    ימוש
    0.09
    תמ
    0.07
    _policy
    0.07
    illiseconds
    0.07
    Fallback
    0.07
     الاقتصادية
    0.07
    Codec
    0.07
    Spec
    0.07
    /{$
    0.07
     yönt
    0.07
    Activations Density 0.002%

    No Known Activations