© 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. 86018
    Prev
    Next
    INDEX
    Explanations

    !

    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
    iesel
    -0.07
     Monad
    -0.07
     capacitor
    -0.07
    谨慎
    -0.06
     fas
    -0.06
    _fore
    -0.06
     ps
    -0.06
     FORE
    -0.06
     xpos
    -0.06
     Dé
    -0.06
    POSITIVE LOGITS
    (xhr
    0.09
    ¯¯
    0.08
    流产
    0.07
    孛
    0.07
     balloon
    0.07
    Wenn
    0.07
    受伤
    0.07
    �
    0.07
    歧视
    0.07
     quilt
    0.07
    Activations Density 0.000%

    No Known Activations