INDEX

Explanations

seems

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

é²Ī

-0.29

gain

-0.25

 Alphabet

-0.25

èĻ¹

-0.25

 ÄĲá»©c

-0.24

è¯ķè¡Į

-0.24

anmar

-0.24

ERIC

-0.24

èĻ¹æ¡¥

-0.24

iscal

-0.23

POSITIVE LOGITS

çĤ¸

0.29

edd

0.28

apo

0.27

æ¥«

0.27

 routes

0.26

_routes

0.26

berger

0.26

routes

0.25

 nearby

0.25

ä»²

0.25

Activations Density 0.002%

seems

No Comments

No Known Activations