INDEX

Explanations

Text snippets

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_18.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.18.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

èĤ¡

-0.31

 vapor

-0.28

èĴ¸æ±½

-0.28

Ab

-0.28

çĪ±

-0.26

 follows

-0.26

vig

-0.25

onden

-0.25

NA

-0.25

Eu

-0.25

POSITIVE LOGITS

`č↵

0.29

è¡ĮæĶ¿æľºåħ³

0.29

åīįç½®

0.29

ograph

0.27

RELATED

0.26

->$

0.26

å°±åľ¨äºİ

0.25

 myster

0.25

å§Ķç»Ħç»ĩ

0.25

 constr

0.24

Activations Density 43.690%

Text snippets

No Comments

No Known Activations