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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 11-RESID-POST-AA
    6. 75567
    Prev
    Next
    INDEX
    Explanations

    antibodies

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    משל
    -0.08
     AudioManager
    -0.07
    เฉ
    -0.07
     Howell
    -0.07
    עצמאי
    -0.07
    纲
    -0.07
    iculos
    -0.07
     traveler
    -0.07
     RECEIVER
    -0.07
    -vector
    -0.06
    POSITIVE LOGITS
    就是因为
    0.07
     dee
    0.07
     define
    0.06
     crist
    0.06
    .removeFrom
    0.06
     faction
    0.06
    功能
    0.06
    ꡓ
    0.06
    _changed
    0.06
     progressive
    0.06
    Activations Density 0.038%

    No Known Activations