© 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. 11-RESID-POST-AA
    11. 24771
    Prev
    Next
    INDEX
    Explanations

    Building with bricks and clay

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ἠ
    -0.07
     [])↵↵
    -0.07
    pour
    -0.06
     JpaRepository
    -0.06
    ifers
    -0.06
    ѹ
    -0.06
     suppressed
    -0.06
    酬
    -0.06
    園
    -0.06
    魄
    -0.06
    POSITIVE LOGITS
    hasil
    0.07
    Wildcard
    0.07
    screen
    0.07
    arn
    0.07
    𬸣
    0.07
     נ
    0.07
     Liam
    0.07
    ideon
    0.07
    iana
    0.07
    了一个
    0.07
    Activations Density 0.007%

    No Known Activations