© 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. 76100
    Prev
    Next
    INDEX
    Explanations

    a, an, of

    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
    应邀
    -0.08
    颇具
    -0.07
    קפ
    -0.07
     Geliş
    -0.07
    |min
    -0.07
     ציבור
    -0.07
    ခ
    -0.07
     אישי
    -0.07
    瓻
    -0.07
     осуществ
    -0.07
    POSITIVE LOGITS
    印记
    0.08
     edits
    0.07
     Driving
    0.07
    ,'"
    0.07
    就跟
    0.07
    standing
    0.07
    exo
    0.07
    atro
    0.06
     livro
    0.06
    빪
    0.06
    Activations Density 0.027%

    No Known Activations