© 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. 13457
    Prev
    Next
    INDEX
    Explanations

    Negative feedback

    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
     reward
    -0.07
     unfore
    -0.07
     diagonal
    -0.07
    Return
    -0.07
    dea
    -0.07
    To
    -0.07
    GU
    -0.07
     pdu
    -0.06
    dim
    -0.06
    »
    -0.06
    POSITIVE LOGITS
    _definitions
    0.08
    缺失
    0.08
    جز
    0.08
    花草
    0.07
    anship
    0.07
    涂抹
    0.07
     Apps
    0.07
    argas
    0.07
     dynamics
    0.07
     smoker
    0.07
    Activations Density 0.391%

    No Known Activations