INDEX

Explanations

gender

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

sign

-0.26

èĲ¥

-0.26

setChecked

-0.26

åľŃ

-0.25

sequence

-0.25

 gland

-0.25

Won

-0.25

éģ®

-0.25

uality

-0.24

seg

-0.24

POSITIVE LOGITS

fsp

0.26

 adult

0.26

Ð°ÑĢÐ°Ð¼

0.25

 Adult

0.25

adult

0.25

ols

0.24

abama

0.24

 Abbas

0.24

SYS

0.24

 endregion

0.24

Activations Density 0.014%

gender

No Comments

No Known Activations