© 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. 42577
    Prev
    Next
    INDEX
    Explanations

    -playing

    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
     He
    -0.07
    .book
    -0.07
     NOR
    -0.07
     Autos
    -0.07
    꽝
    -0.07
    ARDS
    -0.07
    (END
    -0.06
    javax
    -0.06
     jeg
    -0.06
    忠
    -0.06
    POSITIVE LOGITS
    éli
    0.07
     spray
    0.07
     instant
    0.07
    시키
    0.06
    상을
    0.06
    上班族
    0.06
     oppressive
    0.06
    醒来
    0.06
    至上
    0.06
     existing
    0.06
    Activations Density 0.005%

    No Known Activations