INDEX

Explanations

down

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

ouncer

-0.35

edes

-0.28

emons

-0.27

 porr

-0.27

 oblig

-0.27

chantment

-0.26

æīĢæıĲä¾Ľ

-0.26

 dispenser

-0.26

ç½ĳå°ıç¼ĸ

-0.25

EXT

-0.25

POSITIVE LOGITS

nest

0.26

 hoops

0.25

Pet

0.25

åħ³æ³¨åº¦

0.25

IFY

0.24

lip

0.24

MM

0.23

ify

0.23

:]

0.23

CY

0.23

Activations Density 0.004%

down

No Comments

No Known Activations