Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 13622
    Prev
    Next
    INDEX
    Explanations

    set

    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
    izando
    -0.07
     eclipse
    -0.07
     Camb
    -0.07
    不用担心
    -0.07
     Flux
    -0.07
     aux
    -0.07
     нас
    -0.07
    頂
    -0.07
    час
    -0.07
    负
    -0.07
    POSITIVE LOGITS
    >).
    0.07
    _cats
    0.07
    »↵↵
    0.07
    廖
    0.07
    哏
    0.07
    }',
    0.07
     rigged
    0.07
     sets
    0.07
    tparam
    0.07
     Lindsay
    0.06
    Activations Density 0.012%

    No Known Activations