© 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. 30572
    Prev
    Next
    INDEX
    Explanations

    is

    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
    -powered
    -0.07
    (Of
    -0.07
    הלך
    -0.06
    _FAILED
    -0.06
    _WIN
    -0.06
     �
    -0.06
     автомоб
    -0.06
     почему
    -0.06
    _DOC
    -0.06
     dir
    -0.06
    POSITIVE LOGITS
     acquisitions
    0.08
     lays
    0.07
     safe
    0.07
     التركي
    0.07
    ."
↵
    0.07
    exual
    0.07
     lược
    0.07
     allo
    0.07
     Accounts
    0.07
     total
    0.07
    Activations Density 0.003%

    No Known Activations