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. 19-RESID-POST-AA
    6. 8515
    Prev
    Next
    INDEX
    Explanations

    situations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cultivation
    -0.08
     handling
    -0.08
     massage
    -0.07
     gossip
    -0.07
    鲊
    -0.07
     soluble
    -0.07
    _signal
    -0.07
    klass
    -0.07
     Connected
    -0.07
     Gesture
    -0.07
    POSITIVE LOGITS
     أغسط
    0.07
    ventus
    0.07
     Infer
    0.06
    𬱖
    0.06
     whose
    0.06
    ﭬ
    0.06
    его
    0.06
    目标任务
    0.06
    rieg
    0.06
    月至
    0.06
    Activations Density 0.048%

    No Known Activations