INDEX

Explanations

names

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æĬ¹

-0.27

åĨľ

-0.26

hb

-0.25

berman

-0.25

aired

-0.25

{{{

-0.24

 spots

-0.24

 Farmers

-0.24

 airs

-0.24

 farmer

-0.24

POSITIVE LOGITS

ysi

0.27

tha

0.27

à¸łà¸²

0.26

ç½²

0.25

å¿ĥçĲĨåŃ¦

0.25

-property

0.25

fat

0.24

_bi

0.24

.delegate

0.24

èĥ½æ»¡è¶³

0.24

Activations Density 0.002%

names

No Comments

No Known Activations