INDEX

Explanations

code snippets

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_30.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.30.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

half

-0.35

 half

-0.34

åįĬ

-0.32

 demi

-0.31

 Half

-0.31

Half

-0.30

ä¸ĢåįĬ

-0.29

-half

-0.29

 HALF

-0.28

_half

-0.28

POSITIVE LOGITS

ings

0.28

ä¹ĭ

0.27

fires

0.26

exports

0.26

jun

0.25

<<<<<<<

0.25

çĽ¸æ¯Ķä¹ĭä¸ĭ

0.25

feeds

0.24

=-=-=-=-=-=-=-=-

0.24

&view

0.24

Activations Density 0.006%

code snippets

No Known Activations