© 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. 15-RESID-POST-AA
    11. 123463
    Prev
    Next
    INDEX
    Explanations

    Code

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trace
    -0.08
     extend
    -0.06
     אמר
    -0.06
     סיפור
    -0.06
    كم
    -0.06
    נג
    -0.06
     universe
    -0.06
    mittel
    -0.06
     vo
    -0.06
    商品
    -0.06
    POSITIVE LOGITS
    ssl
    0.07
    (argc
    0.07
    lfw
    0.07
    	rs
    0.07
    _responses
    0.07
    Ｆ
    0.07
    随之
    0.07
    ڵ
    0.07
    HasForeignKey
    0.07
    (__('
    0.07
    Activations Density 0.004%

    No Known Activations