INDEX

Explanations

Politics and culture

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_10.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.10.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ëł¨

-0.26

.partial

-0.26

ogy

-0.25

ugin

-0.24

Exist

-0.24

iphy

-0.24

Feature

-0.24

socket

-0.24

 Feature

-0.24

 Plan

-0.24

POSITIVE LOGITS

zier

0.27

 mathematical

0.27

æľĿçĿĢ

0.25

å¸Ĳ

0.24

hex

0.24

 Seah

0.24

chers

0.24

å¤±è´¥

0.24

pv

0.24

 failure

0.23

Activations Density 0.002%

Politics and culture

No Comments

No Known Activations