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. 26079
    Prev
    Next
    INDEX
    Explanations

    Cuba

    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
    ERE
    -0.07
    ㅈ
    -0.07
    ITIES
    -0.07
    有用的
    -0.07
    _ct
    -0.07
     Acts
    -0.07
    _over
    -0.06
    士
    -0.06
     Tiger
    -0.06
    てきて
    -0.06
    POSITIVE LOGITS
    (fc
    0.07
    '\
    0.07
     Warsaw
    0.07
    蚶
    0.07
    #,
    0.07
    ഗ
    0.07
     ("\
    0.07
    تصف
    0.07
     deflect
    0.07
     EEPROM
    0.07
    Activations Density 0.005%

    No Known Activations