INDEX

Explanations

Locations

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

odi

-0.29

èģĶç½ĳ

-0.26

 backs

-0.25

jal

-0.25

rastructure

-0.24

lect

-0.24

porto

-0.24

âĨ©

-0.24

 kháº©u

-0.23

ra

-0.23

POSITIVE LOGITS

MERCHANTABILITY

0.27

è¿ĻæĶ¯

0.26

è¾ķ

0.25

Closure

0.25

æ²Ĳ

0.25

èµļ

0.25

 Riders

0.25

é«ĺåľ°

0.24

åĳ½

0.24

.effects

0.24

Activations Density 0.001%

Locations

No Comments

No Known Activations