INDEX

Explanations

trial

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

acf

-0.30

statt

-0.29

 cháº¯c

-0.28

éľīç´ł

-0.28

ainers

-0.28

 probs

-0.27

 chill

-0.26

ç¾ŀ

-0.26

gom

-0.25

allel

-0.24

POSITIVE LOGITS

roads

0.27

CodeGen

0.27

çĽ²

0.26

ãĥ¼ãĥī

0.26

INGS

0.25

åĬ¨çĶŁæĪĲ

0.25

é£İæ³¢

0.25

 kháº©u

0.25

à¹Ĥà¸ģ

0.24

çļĦç»ıåħ¸

0.24

Activations Density 0.000%

trial

No Comments

No Known Activations