© 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. 19-RESID-POST-AA
    6. 8312
    Prev
    Next
    INDEX
    Explanations

    Explanations and reasons

    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
     everyone
    -0.07
    Jonathan
    -0.07
    谩
    -0.07
     дал
    -0.07
     Neal
    -0.07
    CHKERRQ
    -0.07
     Lös
    -0.07
     Rhode
    -0.07
    Dao
    -0.07
     clustered
    -0.07
    POSITIVE LOGITS
    	cont
    0.07
    bling
    0.07
     surface
    0.07
    amiliar
    0.07
    ;&#
    0.06
    dependent
    0.06
    雪花
    0.06
    depend
    0.06
    -depend
    0.06
    paration
    0.06
    Activations Density 0.250%

    No Known Activations