INDEX

Explanations

possessive pronouns

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

ruption

-0.28

entar

-0.26

pect

-0.26

çĬ¶

-0.26

.pointer

-0.25

uten

-0.25

 muttered

-0.25

 ÑģÐ¾Ð²ÐµÑĢ

-0.25

å¼Ħ

-0.25

ammer

-0.25

POSITIVE LOGITS

true

0.28

ç¤¾ä¼ļåıĳå±ķ

0.27

ableView

0.27

ÃŃda

0.27

ervo

0.26

suf

0.25

 Anthrop

0.25

ÕŃ

0.25

/gif

0.25

sem

0.24

Activations Density 0.001%

possessive pronouns

No Comments

No Known Activations