INDEX

Explanations

training

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

åĴ¥

-0.29

uit

-0.27

-runtime

-0.26

uggle

-0.24

è¿¹

-0.24

_bm

-0.24

/Graphics

-0.24

SHOT

-0.23

æĹı

-0.23

 density

-0.23

POSITIVE LOGITS

åĲ¦

0.28

 backing

0.27

ersions

0.25

ç§°

0.25

å®½

0.25

é¬ĥ

0.25

 ping

0.25

åīĬå¼±

0.24

icles

0.24

á½º

0.24

Activations Density 0.032%

training

No Comments

No Known Activations