INDEX

Explanations

technical text

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

clidean

-0.26

tega

-0.25

 quits

-0.25

 artÄ±k

-0.25

 Terminator

-0.24

ani

-0.24

 preco

-0.24

é¡ºåºı

-0.24

 Leaf

-0.24

èŀº

-0.24

POSITIVE LOGITS

ä¸»åĬĽåĨĽ

0.29

deaux

0.28

ä¹Łæľīä¸ĢäºĽ

0.26

Pooling

0.26

å¢ŀéĩı

0.26

turn

0.24

/loader

0.24

 ones

0.24

sy

0.23

æľº

0.23

Activations Density 0.005%

technical text

No Comments

No Known Activations