INDEX

Explanations

time periods

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

 Ð¿ÑĢÐ°ÐºÑĤÐ¸ÑĩÐµÑģ

-0.28

 Cler

-0.27

 major

-0.27

 Generated

-0.26

 rotated

-0.25

gn

-0.25

 minus

-0.25

 plus

-0.25

Listeners

-0.24

suite

-0.24

POSITIVE LOGITS

_periods

0.27

inky

0.26

 trials

0.26

INET

0.26

INGS

0.26

alom

0.26

Ø¯Ø§Ø¯

0.25

 flakes

0.25

 PropTypes

0.24

ICollection

0.24

Activations Density 0.004%

time periods

No Comments

No Known Activations