© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 41824
    Prev
    Next
    INDEX
    Explanations

    return to work/play

    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
    伝
    -0.07
     cou
    -0.07
    ⎾
    -0.07
    acz
    -0.06
     Alvarez
    -0.06
    ✞
    -0.06
    אמצע
    -0.06
    是他
    -0.06
    fl
    -0.06
    從
    -0.06
    POSITIVE LOGITS
    -spot
    0.08
    匾
    0.08
    ateway
    0.08
     metadata
    0.07
    legant
    0.07
    馄
    0.07
     specs
    0.07
    pora
    0.07
     seeds
    0.07
    _MAC
    0.07
    Activations Density 0.020%

    No Known Activations