© 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. 111328
    Prev
    Next
    INDEX
    Explanations

    words

    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
    LBL
    -0.06
     ESC
    -0.06
    弹
    -0.06
    Drv
    -0.06
    疟
    -0.06
     MessageBoxButtons
    -0.06
    .AddInParameter
    -0.06
    _NM
    -0.06
    阶
    -0.06
    쪽
    -0.06
    POSITIVE LOGITS
    acey
    0.07
    chedules
    0.07
    ÃO
    0.07
    	fill
    0.07
    arem
    0.07
    於是
    0.07
     agreement
    0.07
    أشخاص
    0.07
    دم
    0.07
    olen
    0.07
    Activations Density 0.009%

    No Known Activations