INDEX

Explanations

pull

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

(ib

-0.27

è®¡åĪĴ

-0.25

ijke

-0.25

third

-0.25

 distractions

-0.24

ä»ĸåıĪ

-0.24

:variables

-0.24

 freder

-0.24

ENSIONS

-0.24

 third

-0.24

POSITIVE LOGITS

è¡¨çİ°

0.28

éĹ¾

0.27

å±ķçİ°

0.25

.uni

0.25

åº¾

0.25

ifa

0.25

 TForm

0.24

çª£

0.24

geo

0.24

))-

0.23

Activations Density 0.794%

pull

No Comments

No Known Activations