INDEX

Explanations

disparity

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Spo

-0.25

 Rise

-0.25

ikers

-0.24

rise

-0.24

_PAYMENT

-0.24

stile

-0.23

æ±Ŀ

-0.23

 Ø³ÙĪØ±ÙĬØ©

-0.23

 Ø§ÙĦØ®

-0.23

éģ¨

-0.23

POSITIVE LOGITS

veal

0.27

 roll

0.26

uhan

0.26

 persists

0.26

pite

0.26

nces

0.25

bler

0.25

REV

0.25

¬

0.24

tal

0.24

Activations Density 0.007%

disparity

No Comments

No Known Activations