© 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. 69429
    Prev
    Next
    INDEX
    Explanations

    quart

    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
    科创板
    -0.08
    ele
    -0.07
    小组
    -0.07
    >↵
    -0.07
    埌
    -0.07
    結
    -0.06
    fine
    -0.06
    play
    -0.06
     Group
    -0.06
    ENG
    -0.06
    POSITIVE LOGITS
    ম
    0.07
    _rc
    0.06
     prv
    0.06
     wil
    0.06
     convinc
    0.06
     Purpose
    0.06
    .Calendar
    0.06
    쨌
    0.06
     Prostit
    0.06
    /Application
    0.06
    Activations Density 0.007%

    No Known Activations