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. 15-RESID-POST-AA
    6. 24033
    Prev
    Next
    INDEX
    Explanations

    weak

    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
    assist
    -0.07
    riends
    -0.07
    敢
    -0.07
    $ret
    -0.07
    ℝ
    -0.07
    ksam
    -0.07
    כמות
    -0.07
     lle
    -0.07
    ousing
    -0.07
     outcomes
    -0.06
    POSITIVE LOGITS
     weakness
    0.08
    weighted
    0.07
    _secondary
    0.07
     weak
    0.07
     menor
    0.07
     reviewing
    0.07
     nailed
    0.07
    TableRow
    0.07
    阎
    0.07
     DEFIN
    0.07
    Activations Density 0.014%

    No Known Activations