© 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. 23-RESID-POST-AA
    11. 642
    Prev
    Next
    INDEX
    Explanations

    Links and documentation

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .transforms
    -0.07
    ==
    -0.06
    结合
    -0.06
    _shadow
    -0.06
     Sp
    -0.06
    השקעה
    -0.06
     Spanish
    -0.06
    辒
    -0.06
    permissions
    -0.06
    退还
    -0.06
    POSITIVE LOGITS
     Crud
    0.07
     ücret
    0.07
    รวจ
    0.06
     khá
    0.06
    ACS
    0.06
     digit
    0.06
    롑
    0.06
    几乎所有
    0.06
     غال
    0.06
     Genuine
    0.06
    Activations Density 0.037%

    No Known Activations