© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 25825
    Prev
    Next
    INDEX
    Explanations

    :

    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
     matches
    -0.08
    合作协议
    -0.07
    ศาล
    -0.07
     partida
    -0.07
    곱
    -0.07
    แทน
    -0.06
     vowed
    -0.06
    andid
    -0.06
    ceed
    -0.06
    ichel
    -0.06
    POSITIVE LOGITS
     TypeName
    0.07
     Export
    0.07
    的说法
    0.07
    ਮ
    0.07
    …”↵↵
    0.07
    สะด
    0.07
     Sharp
    0.07
    _extraction
    0.06
    却发现
    0.06
    (length
    0.06
    Activations Density 0.003%

    No Known Activations