INDEX

Explanations

from of

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

 Dating

-0.27

iores

-0.26

Assignable

-0.26

{_

-0.26

vak

-0.24

unal

-0.24

lopedia

-0.24

ioc

-0.24

maal

-0.24

ä¸ĢæĹı

-0.24

POSITIVE LOGITS

 floats

0.28

æĪĲç«ĭ

0.26

 emergency

0.26

äºīè®®

0.25

.pass

0.25

 passes

0.25

imity

0.25

atures

0.25

çİĦ

0.25

ington

0.25

Activations Density 0.002%

from of

No Comments

No Known Activations