© 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. 70176
    Prev
    Next
    INDEX
    Explanations

    overcoming/avoiding

    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
     Nasıl
    -0.07
    Ǚ
    -0.07
    Ꭺ
    -0.07
    蹋
    -0.07
     “[
    -0.06
    'id
    -0.06
    USIC
    -0.06
    ⼟
    -0.06
    “As
    -0.06
    (DialogInterface
    -0.06
    POSITIVE LOGITS
     Crop
    0.08
     Lean
    0.07
     Sovere
    0.07
     wd
    0.07
     ceilings
    0.07
     volum
    0.06
     twin
    0.06
     enrollment
    0.06
    ctrl
    0.06
     Albums
    0.06
    Activations Density 0.010%

    No Known Activations