© 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. 39900
    Prev
    Next
    INDEX
    Explanations

    right-hand

    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
     getType
    -0.07
    .NoArgsConstructor
    -0.07
    /javascript
    -0.07
    畤
    -0.07
    효
    -0.06
    rid
    -0.06
    _ph
    -0.06
    国务院
    -0.06
    .createComponent
    -0.06
    >s
    -0.06
    POSITIVE LOGITS
    バー
    0.08
    -token
    0.08
    -url
    0.07
    وت
    0.07
    _bytes
    0.07
    帮他
    0.07
    讓他
    0.06
    .Comp
    0.06
    ivation
    0.06
    	holder
    0.06
    Activations Density 0.008%

    No Known Activations