© 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
    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. 128752
    Prev
    Next
    INDEX
    Explanations

    the

    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
     """.
    -0.08
    ście
    -0.08
    controls
    -0.07
    新品
    -0.07
    喜欢吃
    -0.07
     completamente
    -0.07
    年由
    -0.07
     daylight
    -0.06
    vanized
    -0.06
    لط
    -0.06
    POSITIVE LOGITS
    .url
    0.07
    Num
    0.06
    턱
    0.06
     channel
    0.06
    (target
    0.06
     hitch
    0.06
    .av
    0.06
    .basic
    0.06
     Blogger
    0.06
     sandals
    0.06
    Activations Density 0.086%

    No Known Activations