© 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. 8331
    Prev
    Next
    INDEX
    Explanations

    explicit

    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
    꼰
    -0.07
    养成
    -0.07
     Derneği
    -0.07
    沮丧
    -0.07
    �
    -0.07
    成了
    -0.07
     laure
    -0.07
    inc
    -0.06
     banned
    -0.06
    Präs
    -0.06
    POSITIVE LOGITS
    的通知
    0.08
     생산
    0.07
    >>,↵
    0.07
    veal
    0.07
    _cid
    0.07
     Fantasy
    0.07
    	HAL
    0.07
    实
    0.07
     hostile
    0.06
    Door
    0.06
    Activations Density 0.000%

    No Known Activations