INDEX

Explanations

conditional words

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

é©±

-0.32

çĪ¹

-0.30

rod

-0.29

(:,:,

-0.27

å¹º

-0.27

 rods

-0.27

 mobil

-0.25

Kind

-0.25

 vessels

-0.24

uy

-0.24

POSITIVE LOGITS

çī¹æľĹ

0.29

bfd

0.26

leta

0.26

iless

0.24

éĩįä¸Ń

0.24

å¤±

0.24

bpp

0.24

lopen

0.24

ograd

0.23

classed

0.23

Activations Density 0.002%

conditional words

No Comments

No Known Activations