INDEX

Explanations

Name fragments

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

ehler

-0.27

á¿Ĩ

-0.26

Ã±e

-0.25

-notes

-0.24

tdown

-0.24

piring

-0.24

Sah

-0.24

 univers

-0.24

psc

-0.24

å¥Ń

-0.24

POSITIVE LOGITS

 verg

0.29

our

0.27

sky

0.27

èĪį

0.26

Fort

0.25

Integrated

0.25

å±ħ

0.25

èľ¡

0.25

ort

0.25

 integrated

0.24

Activations Density 0.092%

Name fragments

No Comments

No Known Activations