INDEX

Explanations

problem

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

bear

-0.27

å®Įå¥½

-0.25

])).

-0.25

]).

-0.24

cheon

-0.24

 tant

-0.24

venge

-0.24

oders

-0.23

ching

-0.23

é£İåħī

-0.23

POSITIVE LOGITS

our

0.28

ecycle

0.28

 deser

0.27

åĶ¿

0.27

æŀ¸

0.26

.resource

0.26

bv

0.25

bv

0.25

bose

0.24

åĵģåĳ³

0.24

Activations Density 25.998%

problem

No Comments

No Known Activations