© 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. 86459
    Prev
    Next
    INDEX
    Explanations

    Code and documentation

    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
     relegated
    -0.08
     remaining
    -0.08
    illian
    -0.07
     Brenda
    -0.07
     Jenny
    -0.07
    空前
    -0.07
    /json
    -0.06
     N
    -0.06
     terms
    -0.06
    );↵↵↵↵
    -0.06
    POSITIVE LOGITS
     détail
    0.08
    不符
    0.07
    _fact
    0.07
    _effects
    0.07
     scratching
    0.07
    yw
    0.07
    하시
    0.07
     ayud
    0.07
     Markt
    0.07
    _draft
    0.07
    Activations Density 0.243%

    No Known Activations