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. 10968
    Prev
    Next
    INDEX
    Explanations

    Business communications

    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
     Secret
    -0.07
    北方
    -0.07
    .create
    -0.07
    yar
    -0.07
    那就
    -0.06
    -windows
    -0.06
    重點
    -0.06
     selective
    -0.06
    巡回
    -0.06
    곽
    -0.06
    POSITIVE LOGITS
     beacon
    0.07
    mdat
    0.07
    /ad
    0.07
    .jd
    0.07
    蟛
    0.07
    磲
    0.07
    acons
    0.07
    告知
    0.07
    Cas
    0.06
     cigarette
    0.06
    Activations Density 0.062%

    No Known Activations